Research from the AI4Forest collaboration.

@misc{Su2028,
  title = {Forest disturbances intensify land surface warming across Europe},
  author = {Su, Yang and Xu, Yidi and Zhang, Xianglin and Makowski, David and Pelissier-Tanon, Agnès and Francini, Saverio and Shi, Tianqi and Yu, Ke and Li, Siyu and Chen, Haotian and Li, Haoruo and Chang, Jinfeng and Chen, Songchao and Yin, Chaohui and Besic, Nikola and Brandt, Martin and Viana-Soto, Alba and Kowalski, Katja and Senf, Cornelius and d’Aspremont, Alexandre and Ciais, Philippe},
  year = {2026},
  doi = {10.21203/rs.3.rs-8782712/v1}
}

@article{Su2026,
  title = {Substantial contribution of trees outside forests to above-ground carbon across China},
  author = {Su, Yang and Shi, Tianqi and Zhang, Xianglin and Xu, Yidi and Cheng, Kai and Liu, Siyu and Han, Ge and Ma, Xin and Chen, Songchao and Tong, Xiaowei and Li, Wei and Gong, Wei and Guo, Qinghua and Brandt, Martin and Piao, Shilong and d’Aspremont, Alexandre and Ciais, Philippe},
  year = {2026},
  journal = {Communications Earth & Environment},
  doi = {10.1038/s43247-025-03150-y}
}

@misc{boudras2026serahnativesentinelspatial,
  title = {SERA-H: Beyond Native Sentinel Spatial Limits for High-Resolution Canopy Height Mapping},
  author = {Boudras, Thomas and Schwartz, Martin and Fensholt, Rasmus and Brandt, Martin and Fayad, Ibrahim and Wigneron, Jean-Pierre and Belouze, Gabriel and Fogel, Fajwel and Ciais, Philippe},
  year = {2026},
  url = {https://arxiv.org/abs/2512.18128}
}

@inproceedings{SchroedterPG2026CanopyTree,
  title = {Canopy Tree Height Estimation using Quantile Regression: Modeling and Evaluating Uncertainty in Remote Sensing},
  author = {Schrödter, Karsten and Pauls, Jan and Gieseke, Fabian},
  year = {2026},
  booktitle = {Proceedings of the 29th Annual Conference on Artificial Intelligence and Statistics (AISTATS)},
  url = {https://arxiv.org/abs/2604.06988}
}

@inproceedings{schroedter2026bitwisequant,
  title = {Trainable Bitwise Soft Quantization for Input Feature Compression},
  author = {Schrödter, Karsten and Stenkamp, Jan and Herrmann, Nina and Gieseke, Fabian},
  year = {2026},
  booktitle = {Third Conference on Parsimony and Learning (CPAL)},
  url = {https://www.mldelab.de/publications/}
}

@misc{Su2027,
  title = {A fused canopy height map of Italy (2004–2024) from spaceborne and airborne LiDAR, and Landsat via deep learning and Bayesian averaging},
  author = {Su, Yang and Besic, Nikola and Zhang, Xianglin and Xu, Yidi and Francini, Saverio and D’Amico, Giovanni and Chirici, Gherardo and Schwartz, Martin and Fayad, Ibrahim and Brood, Sarah and Pellissier-tanon, Agnes and Yu, Ke and Chen, Haotian and Chen, Songchao and d’Aspremont, Alexandre and Ciais, Philippe},
  year = {2025},
  doi = {10.5194/essd-2025-378}
}

@misc{viana_soto_senf_2025_reburns,
  title = {Forest reburns are integral to southern Europe’s disturbance regimes},
  author = {Viana-Soto, Alba and Senf, Cornelius},
  year = {2025},
  doi = {10.21203/rs.3.rs-6937064/v1}
}

@article{Su2025,
  title = {Canopy height and biomass distribution across the forests of Iberian Peninsula},
  author = {Su, Yang and Schwartz, Martin and Fayad, Ibrahim and García, Mariano and Zavala, Miguel A. and Tijerín-Triviño, Julián and Astigarraga, Julen and Cruz-Alonso, Verónica and Liu, Siyu and Zhang, Xianglin and Chen, Songchao and Ritter, François and Besic, Nikola and d’Aspremont, Alexandre and Ciais, Philippe},
  year = {2025},
  journal = {Scientific Data},
  doi = {10.1038/s41597-025-05021-9}
}

@article{gmd-18-337-2025,
  title = {Remote-sensing-based forest canopy height mapping: some models are useful, but might they provide us with even more insights when combined?},
  author = {Besic, N. and Picard, N. and Vega, C. and Bontemps, J.-D. and Hertzog, L. and Renaud, J.-P. and Fogel, F. and Schwartz, M. and Pellissier-Tanon, A. and Destouet, G. and Mortier, F. and Planells-Rodriguez, M. and Ciais, P.},
  year = {2025},
  journal = {Geoscientific Model Development},
  doi = {10.5194/gmd-18-337-2025},
  url = {https://gmd.copernicus.org/articles/18/337/2025/}
}

@inproceedings{pauls2025capturing,
  title = {Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation},
  author = {Pauls, Jan and Zimmer, Max and Turan, Berkant and Saatchi, Sassan and Ciais, Philippe and Pokutta, Sebastian and Gieseke, Fabian},
  year = {2025},
  booktitle = {International Conference on Machine Learning (ICML)},
  url = {https://arxiv.org/abs/2501.19328}
}

@inproceedings{fayad2025dunia,
  title = {DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications},
  author = {Fayad, Ibrahim and Zimmer, Max and Schwartz, Martin and Ciais, Philippe and Gieseke, Fabian and Belouze, Gabriel and Brood, Sarah and De Truchis, Aurelien and d’Aspremont, Alexandre},
  year = {2025},
  booktitle = {International Conference on Machine Learning (ICML)},
  url = {https://arxiv.org/abs/2502.17066}
}

@article{zimmer2025sparseswaps,
  title = {SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale},
  author = {Zimmer, Max and Roux, Christophe and Wagner, Moritz and Hendrych, Deborah and Pokutta, Sebastian},
  year = {2025},
  journal = {arXiv preprint arXiv:2512.10922},
  doi = {10.48550/arXiv.2512.10922}
}

@inbook{ZimmerSpiegelPokutta+2025+137+168,
  title = {Compression-aware Training of Neural Networks using Frank-Wolfe},
  author = {Zimmer, Max and Spiegel, Christoph and Pokutta, Sebastian},
  year = {2025},
  booktitle = {Mathematical Optimization for Machine Learning},
  doi = {10.1515/9783111376776-010},
  url = {https://doi.org/10.1515/9783111376776-010}
}

@article{schwartz_high-resolution_2024,
  title = {High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach},
  author = {Schwartz, Martin and Ciais, Philippe and Ottlé, Catherine and De Truchis, Aurelien and Vega, Cedric and Fayad, Ibrahim and Brandt, Martin and Fensholt, Rasmus and Baghdadi, Nicolas and Morneau, François and Morin, David and Guyon, Dominique and Dayau, Sylvia and Wigneron, Jean-Pierre},
  year = {2024},
  journal = {International Journal of Applied Earth Observation and Geoinformation},
  doi = {10.1016/j.jag.2024.103711},
  url = {https://www.sciencedirect.com/science/article/pii/S1569843224000657}
}

@article{fogel2024opencanopy,
  title = {Open-Canopy: Towards Very High Resolution Forest Monitoring},
  author = {Fogel, François and Schwartz, Martin and Ciais, Philippe and De Truchis, Aurélien and Vega, Cedric and Fayad, Ibrahim and Brandt, Martin},
  year = {2024},
  journal = {arXiv preprint arXiv:2407.09392},
  url = {https://arxiv.org/abs/2407.09392}
}

@inproceedings{pauls2024estimating,
  title = {Estimating canopy height at scale},
  author = {Pauls, Jan and Zimmer, Max and Kelly, Una M and Schwartz, Martin and Saatchi, Sassan and Ciais, Philippe and Pokutta, Sebastian and Brandt, Martin and Gieseke, Fabian},
  year = {2024},
  booktitle = {International Conference on Machine Learning (ICML)},
  url = {https://arxiv.org/abs/2406.01076}
}

@article{VianaSotoandSenf2024,
  title = {The European Forest Disturbance Atlas: a forest disturbance monitoring system using the Landsat archive},
  author = {Viana-Soto, Alba and Senf, Cornelius and Sebald, Julian and Seidl, Rupert},
  year = {2024},
  journal = {Earth System Science Data Discussions},
  url = {https://essd.copernicus.org/preprints/essd-2024-123/}
}

@article{schwartz_forms_2023,
  title = {FORMS: Forest Multiple Source height, wood volume, and biomass maps in France at 10 to 30 m resolution based on Sentinel-1, Sentinel-2, and Global Ecosystem Dynamics Investigation (GEDI) data with a deep learning approach},
  author = {Schwartz, Martin and Ciais, Philippe and De Truchis, Aurélien and Chave, Jérôme and Ottlé, Catherine and Vega, Cedric and Wigneron, Jean-Pierre and Nicolas, Manuel and Jouaber, Sami and Liu, Siyu and Brandt, Martin and Fayad, Ibrahim},
  year = {2023},
  journal = {Earth System Science Data},
  doi = {10.5194/essd-15-4927-2023},
  url = {https://essd.copernicus.org/articles/15/4927/2023/}
}

@article{VIANASOTO2022113239,
  title = {Quantifying post-fire shifts in woody-vegetation cover composition in Mediterranean pine forests using Landsat time series and regression-based unmixing},
  author = {Viana-Soto, Alba and Okujeni, Akpona and Pflugmacher, Dirk and García, Mariano and Aguado, Inmaculada and Hostert, Patrick},
  year = {2022},
  journal = {Remote Sensing of Environment},
  doi = {10.1016/j.rse.2022.113239},
  url = {https://www.sciencedirect.com/science/article/pii/S0034425722003455}
}